Mostra el registre d'ítem simple
Neural network language models to select the best translation
dc.contributor.author | Khalilov, Maxim |
dc.contributor.author | Rodríguez Fonollosa, José Adrián |
dc.contributor.author | Zamora Martínez, Francisco |
dc.contributor.author | Castro Bleda, María José |
dc.contributor.author | España Boquera, Salvador |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions |
dc.date.accessioned | 2013-12-31T08:47:39Z |
dc.date.available | 2013-12-31T08:47:39Z |
dc.date.created | 2013-12-20 |
dc.date.issued | 2013-12-20 |
dc.identifier.citation | Khalilov, M. [et al.]. Neural network language models to select the best translation. "Computational Linguistics in the Netherlands Journal", 20 Desembre 2013, vol. 3, p. 217-233. |
dc.identifier.issn | 2211-4009 |
dc.identifier.uri | http://hdl.handle.net/2117/21106 |
dc.description.abstract | The quality of translations produced by statistical machine translation (SMT) systems crucially depends on the generalization ability provided by the statistical models involved in the process. While most modern SMT systems use n-gram models to predict the next element in a sequence of tokens, our system uses a continuous space language model (LM) based on neural networks (NN). In contrast to works in which the NN LM is only used to estimate the probabilities of shortlist words (Schwenk 2010), we calculate the posterior probabilities of out-of-shortlist words using an additional neuron and unigram probabilities. Experimental results on a small Italian- to-English and a large Arabic-to-English translation task, which take into account di erent word history lengths (n-gram order), show that the NN LMs are scalable to small and large data and can improve an n-gram-based SMT system. For the most part, this approach aims to improve translation quality for tasks that lack translation data, but we also demonstrate its scalability to large-vocabulary tasks. |
dc.format.extent | 17 p. |
dc.language.iso | eng |
dc.rights | Attribution-NonCommercial-NoDerivs 3.0 Spain |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural |
dc.subject.lcsh | Natural language processing (Computer science) |
dc.subject.lcsh | Automatic speech recognition |
dc.title | Neural network language models to select the best translation |
dc.type | Article |
dc.subject.lemac | Tractament del llenguatge natural (Informàtica) |
dc.subject.lemac | Reconeixement automàtic de la parla |
dc.contributor.group | Universitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | http://clinjournal.org/sites/default/files/13-Khalilov-etal-CLIN2013.pdf |
dc.rights.access | Open Access |
local.identifier.drac | 12952247 |
dc.description.version | Postprint (published version) |
local.citation.author | Khalilov, M.; Fonollosa, José A. R.; Zamora-Martínez, F.; Castro-Bleda, M.J.; España-Boquera, S. |
local.citation.publicationName | Computational Linguistics in the Netherlands Journal |
local.citation.volume | 3 |
local.citation.startingPage | 217 |
local.citation.endingPage | 233 |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Articles de revista [172]
-
Articles de revista [2.528]